Spreadsheet Task Execution on SpreadsheetBench Full
47.42Soft ScoreSkillCAT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 47.42 | 31.91 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 47.17 | 29.53 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 45.18 | 31.14 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 42.47 | 29.82 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 40.73 | 24.45 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 39.35 | 19.41 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 39.02 | 20.61 | |
| No-SkillSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 36.84 | 25.22 | |
| No-SkillSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 36.84 | 25.22 | |
| ParametricSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 36.6 | 17.5 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 36.3 | 17.03 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 27.37 | 16.1 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 25.18 | 10.75 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 23.76 | 16.89 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 23.76 | 16.89 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 22.22 | 11.51 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 18.8 | 5.73 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 18.42 | 9.43 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 18.42 | 9.43 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 18.1 | 5.13 | |
| No-SkillSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 14.88 | 5.7 | |
| No-SkillSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 14.88 | 5.7 | |
| ParametricSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 13.7 | 3.87 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 13.03 | 3.37 |